© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129884
    Prev
    Next
    INDEX
    Explanations

    Digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONENT
    -0.26
     sick
    -0.25
    åĽ½
    -0.24
     deterior
    -0.24
     buc
    -0.23
     street
    -0.23
     kicker
    -0.23
    elier
    -0.23
    Äħż
    -0.23
    oad
    -0.23
    POSITIVE LOGITS
    éĹŃ
    0.28
    raq
    0.28
    åĩ¸
    0.27
     #:
    0.27
    recur
    0.27
     STATS
    0.26
    çĽĨåľ°
    0.24
    åįģä¸īäºĶ
    0.24
    åįĴ
    0.24
    å¹³åı°ä¸Ĭ
    0.24
    Activations Density 0.002%

    No Known Activations